from os.path import dirname as dn, join as jn

#to get the rhodecode import

sys.path.append(dn(dn(dn(os.path.realpath(__file__)))))

from string import strip

from shutil import rmtree

from whoosh.analysis import RegexTokenizer, LowercaseFilter, StopFilter

from whoosh.fields import TEXT, ID, STORED, NUMERIC, BOOLEAN, Schema, FieldType

from whoosh.index import create_in, open_dir

from whoosh.formats import Characters

from whoosh.highlight import highlight, HtmlFormatter, ContextFragmenter

from webhelpers.html.builder import escape, literal

from sqlalchemy import engine_from_config

from rhodecode.model import init_model

from rhodecode.model.scm import ScmModel

from rhodecode.model.repo import RepoModel

from rhodecode.config.environment import load_environment

from rhodecode.lib.utils2 import LazyProperty

from rhodecode.lib.utils import BasePasterCommand, Command, add_cache,\

    load_rcextensions

log = logging.getLogger(__name__)

# CUSTOM ANALYZER wordsplit + lowercase filter

ANALYZER = RegexTokenizer(expression=r"\w+") | LowercaseFilter()

#INDEX SCHEMA DEFINITION

SCHEMA = Schema(

    fileid=ID(unique=True),

    owner=TEXT(),

    repository=TEXT(stored=True),

    path=TEXT(stored=True),

    content=FieldType(format=Characters(), analyzer=ANALYZER,

                      scorable=True, stored=True),

    modtime=STORED(),

    extension=TEXT(stored=True)

)

IDX_NAME = 'HG_INDEX'

FORMATTER = HtmlFormatter('span', between='\n<span class="break">...</span>\n')

FRAGMENTER = ContextFragmenter(200)

CHGSETS_SCHEMA = Schema(

    raw_id=ID(unique=True, stored=True),

    last=BOOLEAN(),

    owner=TEXT(),

    repository=ID(unique=True, stored=True),

    author=TEXT(stored=True),

    message=FieldType(format=Characters(), analyzer=ANALYZER,

                      scorable=True, stored=True),

    parents=TEXT(),

    added=TEXT(),

    removed=TEXT(),

    changed=TEXT(),

)

CHGSET_IDX_NAME = 'CHGSET_INDEX'

class MakeIndex(BasePasterCommand):

    max_args = 1

    min_args = 1

    usage = "CONFIG_FILE"

    summary = "Creates index for full text search given configuration file"

    group_name = "RhodeCode"

    takes_config_file = -1

    parser = Command.standard_parser(verbose=True)

    def command(self):

        logging.config.fileConfig(self.path_to_ini_file)

        from pylons import config

        add_cache(config)

        engine = engine_from_config(config, 'sqlalchemy.db1.')

        init_model(engine)

        index_location = config['index_dir']

        repo_location = self.options.repo_location \

            if self.options.repo_location else RepoModel().repos_path

        repo_list = map(strip, self.options.repo_list.split(',')) \

            if self.options.repo_list else None

        repo_update_list = map(strip, self.options.repo_update_list.split(',')) \

            if self.options.repo_update_list else None

        load_rcextensions(config['here'])

        #======================================================================

        # WHOOSH DAEMON

        #======================================================================

        from rhodecode.lib.pidlock import LockHeld, DaemonLock

        from rhodecode.lib.indexers.daemon import WhooshIndexingDaemon

        try:

            l = DaemonLock(file_=jn(dn(dn(index_location)), 'make_index.lock'))

            WhooshIndexingDaemon(index_location=index_location,

                                 repo_location=repo_location,

                log.debug('    >> %s [WITH CONTENT]' % path)

                indexed_w_content += 1

        else:

            log.debug('    >> %s' % path)

            # just index file name without it's content

            u_content = u''

            indexed += 1

        p = safe_unicode(path)

        writer.add_document(

            fileid=p,

            owner=unicode(repo.contact),

            repository=safe_unicode(repo_name),

            path=p,

            content=u_content,

            modtime=self.get_node_mtime(node),

            extension=node.extension

        )

        return indexed, indexed_w_content

    def index_changesets(self, writer, repo_name, repo, start_rev=None):

        """

        Add all changeset in the vcs repo starting at start_rev

        to the index writer

        :param writer: the whoosh index writer to add to

        :param repo_name: name of the repository from whence the

          changeset originates including the repository group

        :param repo: the vcs repository instance to index changesets for,

          the presumption is the repo has changesets to index

        :param start_rev=None: the full sha id to start indexing from

          if start_rev is None then index from the first changeset in

          the repo

        """

        if start_rev is None:

            start_rev = repo[0].raw_id

        log.debug('indexing changesets in %s starting at rev: %s' %

                  (repo_name, start_rev))

        indexed = 0

        for cs in repo.get_changesets(start=start_rev):

            log.debug('    >> %s' % cs)

            writer.add_document(

                raw_id=unicode(cs.raw_id),

                owner=unicode(repo.contact),

                repository=safe_unicode(repo_name),

                author=cs.author,

                message=cs.message,

                last=cs.last,

                added=u' '.join([node.path for node in cs.added]).lower(),

                removed=u' '.join([node.path for node in cs.removed]).lower(),

                changed=u' '.join([node.path for node in cs.changed]).lower(),

                parents=u' '.join([cs.raw_id for cs in cs.parents]),

            )

            indexed += 1

        log.debug('indexed %d changesets for repo %s' % (indexed, repo_name))

        return indexed

    def index_files(self, file_idx_writer, repo_name, repo):

        """

        Index files for given repo_name

        :param file_idx_writer: the whoosh index writer to add to

        :param repo_name: name of the repository we're indexing

        :param repo: instance of vcs repo

        """

        i_cnt = iwc_cnt = 0

        log.debug('building index for [%s]' % repo.path)

        for idx_path in self.get_paths(repo):

            i, iwc = self.add_doc(file_idx_writer, idx_path, repo, repo_name)

            i_cnt += i

            iwc_cnt += iwc

        log.debug('added %s files %s with content for repo %s' %

                  (i_cnt + iwc_cnt, iwc_cnt, repo.path))

        return i_cnt, iwc_cnt

    def update_changeset_index(self):

        idx = open_dir(self.index_location, indexname=CHGSET_IDX_NAME)

        with idx.searcher() as searcher:

            writer = idx.writer()

            writer_is_dirty = False

            try:

                indexed_total = 0

                for repo_name, repo in self.repo_paths.items():

                    # skip indexing if there aren't any revs in the repo

                    num_of_revs = len(repo)

                    if num_of_revs < 1:

                        continue

                    qp = QueryParser('repository', schema=CHGSETS_SCHEMA)

from rhodecode.lib.vcs.utils import safe_unicode

from rhodecode.lib.vcs.utils import date_fromtimestamp

from rhodecode.lib.vcs.utils.lazy import LazyProperty

class GitChangeset(BaseChangeset):

    """

    Represents state of the repository at single revision.

    """

    def __init__(self, repository, revision):

        self._stat_modes = {}

        self.repository = repository

        try:

            commit = self.repository._repo.get_object(revision)

            if isinstance(commit, objects.Tag):

                revision = commit.object[1]

                commit = self.repository._repo.get_object(commit.object[1])

        except KeyError:

            raise RepositoryError("Cannot get object with id %s" % revision)

        self.raw_id = revision

        self.id = self.raw_id

        self.short_id = self.raw_id[:12]

        self._commit = commit

        self._tree_id = commit.tree

        self._commiter_property = 'committer'

        self._date_property = 'commit_time'

        self._date_tz_property = 'commit_timezone'

        self.revision = repository.revisions.index(revision)

        self.message = safe_unicode(commit.message)

        #self.branch = None

        self.tags = []

        self.nodes = {}

        self._paths = {}

    @LazyProperty

    def author(self):

        return safe_unicode(getattr(self._commit, self._commiter_property))

    @LazyProperty

    def date(self):

        return date_fromtimestamp(getattr(self._commit, self._date_property),

                                  getattr(self._commit, self._date_tz_property))

    @LazyProperty

    def status(self):

        """

        Returns modified, added, removed, deleted files for current changeset

        """

        return self.changed, self.added, self.removed

    @LazyProperty

    def branch(self):

        heads = self.repository._heads(reverse=False)

        ref = heads.get(self.raw_id)

        if ref:

            return safe_unicode(ref)

    def _fix_path(self, path):

        """

        Paths are stored without trailing slash so we need to get rid off it if

        needed.

        """

        if path.endswith('/'):

            path = path.rstrip('/')

        return path

    def _get_id_for_path(self, path):

        # FIXME: Please, spare a couple of minutes and make those codes cleaner;

        if not path in self._paths:

            path = path.strip('/')

            # set root tree

            tree = self.repository._repo[self._tree_id]

            if path == '':

                self._paths[''] = tree.id

                return tree.id

            splitted = path.split('/')

            dirs, name = splitted[:-1], splitted[-1]

            curdir = ''

            # initially extract things from root dir

            for item, stat, id in tree.iteritems():

                if curdir:

                    name = '/'.join((curdir, item))

                else:

                    name = item

                self._paths[name] = id

                self._stat_modes[name] = stat

            for dir in dirs:

    ChangesetError, ImproperArchiveTypeError, NodeDoesNotExistError, VCSError

from rhodecode.lib.vcs.nodes import AddedFileNodesGenerator, \

    ChangedFileNodesGenerator, DirNode, FileNode, NodeKind, \

    RemovedFileNodesGenerator, RootNode, SubModuleNode

from rhodecode.lib.vcs.utils import safe_str, safe_unicode, date_fromtimestamp

from rhodecode.lib.vcs.utils.lazy import LazyProperty

from rhodecode.lib.vcs.utils.paths import get_dirs_for_path

from rhodecode.lib.vcs.utils.hgcompat import archival, hex

class MercurialChangeset(BaseChangeset):

    """

    Represents state of the repository at the single revision.

    """

    def __init__(self, repository, revision):

        self.repository = repository

        self.raw_id = revision

        self._ctx = repository._repo[revision]

        self.revision = self._ctx._rev

        self.nodes = {}

    @LazyProperty

    def tags(self):

        return map(safe_unicode, self._ctx.tags())

    @LazyProperty

    def branch(self):

        return  safe_unicode(self._ctx.branch())

    @LazyProperty

    def bookmarks(self):

        return map(safe_unicode, self._ctx.bookmarks())

    @LazyProperty

    def message(self):

        return safe_unicode(self._ctx.description())

    @LazyProperty

    def author(self):

        return safe_unicode(self._ctx.user())

    @LazyProperty

    def date(self):

        return date_fromtimestamp(*self._ctx.date())

    @LazyProperty

    def status(self):

        """

        Returns modified, added, removed, deleted files for current changeset

        """

        return self.repository._repo.status(self._ctx.p1().node(),

                                            self._ctx.node())

    @LazyProperty

    def _file_paths(self):

        return list(self._ctx)

    @LazyProperty

    def _dir_paths(self):

        p = list(set(get_dirs_for_path(*self._file_paths)))

        p.insert(0, '')

        return p

    @LazyProperty

    def _paths(self):

        return self._dir_paths + self._file_paths

    @LazyProperty

    def id(self):

        if self.last:

            return u'tip'

        return self.short_id

    @LazyProperty

    def short_id(self):

        return self.raw_id[:12]

    @LazyProperty

    def parents(self):

        """

        Returns list of parents changesets.

        """

        return [self.repository.get_changeset(parent.rev())

                for parent in self._ctx.parents() if parent.rev() >= 0]

    def next(self, branch=None):

        if branch and self.branch != branch:

            raise VCSError('Branch option used on changeset not belonging '

                           'to that branch')

        def _next(changeset, branch):

            try:

                next_ = changeset.revision + 1